app.py

import os
import gradio as gr
import numpy as np
import tensorflow as tf
from transformers import pipeline
from dotenv import load_dotenv
import nltk

# Load environment variables from .env file
load_dotenv()
hf_api_key = os.getenv("HUGGING_FACE_KEY")

# Initialize Hugging Face Text Generation Pipeline
llama_model = "meta-llama/Meta-Llama-3.1-8B-Instruct"
text_generator = pipeline("text-generation", model=llama_model, use_auth_token=hf_api_key)

# Load the TensorFlow model
model = tf.keras.models.load_model("resume_generator_model.h5")

# Define helper functions
def enhance_with_huggingface(resume_text, job_title):
    """Generate enhanced resume content using Llama."""
    prompt = f"Enhance the following resume for the job title '{job_title}': {resume_text}"
    response = text_generator(prompt, max_length=500, num_return_sequences=1)
    return response[0]['generated_text']

def enhance_with_local_model(resume_text, job_title):
    """Generate enhancements using local TensorFlow model."""
    # Placeholder example: Use some custom logic for enhancement based on the local model.
    sample_input = np.array([[len(resume_text.split()), len(job_title.split())]])
    enhancement_score = model.predict(sample_input)
    return f"Enhanced (Local Model) - Score: {enhancement_score[0][0]:.2f}"

# Define the function to handle resume enhancements
def enhance_resume(uploaded_resume, job_title):
    """Main enhancement function."""
    # Extract text from the uploaded file
    resume_text = uploaded_resume.read().decode('utf-8')

    # Use both models for enhancements
    llama_enhanced_resume = enhance_with_huggingface(resume_text, job_title)
    local_enhanced_resume = enhance_with_local_model(resume_text, job_title)

    # Combine results from both models
    enhanced_resume = f"{llama_enhanced_resume}\n\n{local_enhanced_resume}"
    return enhanced_resume

# Create a Gradio interface
inputs = [
    gr.inputs.File(label="Upload your Resume (TXT)", type="file"),
    gr.inputs.Textbox(label="Job Title", placeholder="e.g., Data Scientist"),
]

outputs = gr.outputs.Textbox(label="Enhanced Resume")

# Create a Gradio Interface
app = gr.Interface(
    fn=enhance_resume,
    inputs=inputs,
    outputs=outputs,
    title="Resume Enhancer",
    description="Enhance your resume based on the given job title using AI models.",
)

# Run the app
if __name__ == "__main__":
    app.launch()